SOTAVerified

Unsupervised Semantic Segmentation

Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.

( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 95 papers

TitleStatusHype
Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20^th century Urban Landscapes with Satellite ImageriesCode2
LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point CloudsCode1
Federated Unsupervised Semantic Segmentation—0
Hierarchical Context Learning of object components for unsupervised semantic segmentationCode0
Scene-Centric Unsupervised Panoptic SegmentationCode2
COIN: Confidence Score-Guided Distillation for Annotation-Free Cell SegmentationCode0
NPSim: Nighttime Photorealistic Simulation From Daytime Images With Monocular Inverse Rendering and Ray Tracing—0
GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel ClusteringCode0
ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding—0
Unsupervised semantic segmentation of urban high-density multispectral point clouds—0
CUS3D :CLIP-based Unsupervised 3D Segmentation via Object-level Denoise—0
Segmentation by Factorization: Unsupervised Semantic Segmentation for Pathology by Factorizing Foundation Model Features—0
iSeg: An Iterative Refinement-based Framework for Training-free SegmentationCode1
ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic SegmentationCode2
Progressive Proxy Anchor Propagation for Unsupervised Semantic SegmentationCode1
Deep ContourFlow: Advancing Active Contours with Deep LearningCode1
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized CutCode2
DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial ContinuityCode0
Boosting Unsupervised Semantic Segmentation with Principal Mask ProposalsCode1
OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation—0
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic SegmentationCode2
Applying Unsupervised Semantic Segmentation to High-Resolution UAV Imagery for Enhanced Road Scene ParsingCode0
DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision TransformerCode0
Learn to Rectify the Bias of CLIP for Unsupervised Semantic SegmentationCode2
SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation—0
Unsupervised Universal Image SegmentationCode2
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization—0
A Lightweight Clustering Framework for Unsupervised Semantic Segmentation—0
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation—0
Overhead Line Defect Recognition Based on Unsupervised Semantic Segmentation—0
SmooSeg: Smoothness Prior for Unsupervised Semantic SegmentationCode1
Pixel-Level Clustering Network for Unsupervised Image Segmentation—0
Causal Unsupervised Semantic SegmentationCode1
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and SamplingCode1
A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications—0
Time Does Tell: Self-Supervised Time-Tuning of Dense Image RepresentationsCode1
Optical Flow boosts Unsupervised Localization and SegmentationCode1
Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic GroupingCode1
GrowSP: Unsupervised Semantic Segmentation of 3D Point CloudsCode1
Component-aware anomaly detection framework for adjustable and logical industrial visual inspectionCode1
PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel ClusteringCode1
Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic SegmentationCode1
Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation—0
Removing supervision in semantic segmentation with local-global matching and area balancingCode0
Leveraging Hidden Positives for Unsupervised Semantic SegmentationCode1
CrOC: Cross-View Online Clustering for Dense Visual Representation LearningCode1
ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical ImagesCode0
SILOP: An Automated Framework for Semantic Segmentation Using Image Labels Based on Object PerimetersCode0
DMSA: Dynamic Multi-scale Unsupervised Semantic Segmentation Based on Adaptive AffinityCode0
PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel ClusteringCode1
Show:102550
← PrevPage 1 of 2Next →
All datasetsCOCO-Stuff-27Cityscapes testPASCAL VOC 2012 valPotsdam-3COCO-Stuff-3ImageNet-S-50COCO-Stuff-171COCO-Stuff-81SUIMCOCO-Stuff-15ACDC (Adverse Conditions Dataset with Correspondences)Cityscapes val

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SGSegClustering [Accuracy]55.7—Unverified
2DynaSeg - FSF (ResNet-18 FPN)Clustering [mIoU]54.1—Unverified
3SANClustering [Accuracy]52—Unverified
4DiffCutClustering [mIoU]49.1—Unverified
5PiCIEClustering [Accuracy]48.1—Unverified
6HCL (ViT-S/8)Linear Classifier [mIoU]47.4—Unverified
7HCL (ViT-S/16)Linear Classifier [mIoU]45.8—Unverified
8CAUSE (DINOv2, ViT-B/14)Clustering [mIoU]45.3—Unverified
9Ours (SlotCon)Clustering [Accuracy]42.36—Unverified
10CAUSE (ViT-B/8)Clustering [mIoU]41.9—Unverified
#ModelMetricClaimedVerifiedStatus
1GraPixPixel Accuracy64.89—Unverified
2CUPSmIoU26.8—Unverified
3ViCEmIoU25.2—Unverified
4EAGLE (DINO, ViT-B/8)mIoU22.1—Unverified
5EQUSSmIoU22—Unverified
6PriMaPs-EM + STEGO (DINO ViT-B/8)mIoU21.6—Unverified
7STEGOmIoU21—Unverified
8EAGLE (DINO, ViT-S/8)mIoU19.7—Unverified
9PriMaPs-EM (DINO ViT-S/8)mIoU19.4—Unverified
10HPmIoU18.4—Unverified
#ModelMetricClaimedVerifiedStatus
1CAUSE (iBOT, ViT-B/16)Clustering [mIoU]53.4—Unverified
2CAUSE (ViT-B/8)Clustering [mIoU]53.3—Unverified
3CAUSE (DINOv2, ViT-B/14)Clustering [mIoU]53.2—Unverified
4MaskDistill+CRFClustering [mIoU]48.9—Unverified
5Leopart (ViT-B/8)Clustering [mIoU]47.2—Unverified
6HCL (ViT-S/8)Clustering [mIoU]46.3—Unverified
7MaskDistillClustering [mIoU]45.8—Unverified
8MaskContrast (Saliency)Clustering [mIoU]44.2—Unverified
9HCL (ViT-S/16)Clustering [mIoU]43.2—Unverified
10Leopart (ViT-S/16)Clustering [mIoU]41.7—Unverified
#ModelMetricClaimedVerifiedStatus
1EAGLE (DINO, ViT-B/8)Accuracy83.3—Unverified
2PriMaPs-EM+HP (DINO ViT-B/8)Accuracy83.3—Unverified
3HPAccuracy82.4—Unverified
4EQUSSAccuracy82—Unverified
5PriMaPs-EM (DINO ViT-B/8)Accuracy80.5—Unverified
6STEGOAccuracy77—Unverified
7InfoSegPixel Accuracy71.6—Unverified
8IICAccuracy45.4—Unverified
#ModelMetricClaimedVerifiedStatus
1SANPixel Accuracy80.3—Unverified
2SGSegPixel Accuracy74.6—Unverified
3InfoSegPixel Accuracy73.8—Unverified
4InMARSPixel Accuracy73.1—Unverified
5ACPixel Accuracy72.9—Unverified
6IICPixel Accuracy72.3—Unverified
#ModelMetricClaimedVerifiedStatus
1PASS (+Saliency map)mIoU (test)42.3—Unverified
2PASSmIoU (test)32—Unverified
3MaskContrast (+Saliency map)mIoU (test)24.2—Unverified
4PiCIE (Supervised pretrain)mIoU (test)17.6—Unverified
5MDC (Supervised pretrain)mIoU (test)14.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CAUSE-TR (ViT-S/8)mIoU15.2—Unverified
2TransFGU (ViT-S/8)mIoU11.93—Unverified
3PiCIE (ResNet-50)mIoU5.6—Unverified
4IIC (ResNet-50)mIoU2.2—Unverified
#ModelMetricClaimedVerifiedStatus
1CAUSE-TR (ViT-S/8)mIoU21.2—Unverified
2CAUSE-MLP (ViT-S/8)mIoU19.1—Unverified
3TransFGU (ViT-S/8)mIoU12.7—Unverified
4MaskContrast (ResNet-50)mIoU3.7—Unverified
#ModelMetricClaimedVerifiedStatus
1DatUS (ViT-B/8) + OCPixel Accuracy69.98—Unverified
2GraPix + AUTPixel Accuracy65.48—Unverified
3DatUS (ViT-B/8)Pixel Accuracy64.67—Unverified
4GraPixPixel Accuracy64.06—Unverified
#ModelMetricClaimedVerifiedStatus
1InfoSegPixel Accuracy38.8—Unverified
2InMARSPixel Accuracy31—Unverified
3IICPixel Accuracy27.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Segmenter ViT-S/16mIoU16.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Segmenter ViT-S/16mIoU21.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DenseSiammIoU16.4—Unverified
#ModelMetricClaimedVerifiedStatus
1InfoSegPixel Accuracy69.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Segmenter ViT-S/16mIoU14.2—Unverified
#ModelMetricClaimedVerifiedStatus
1PASSmIoU (test)11—Unverified
#ModelMetricClaimedVerifiedStatus
1PASSmIoU (test)18.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Segmenter ViT-S/16mIoU18.9—Unverified